Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

1 files changed, 41 insertions, 52 deletions

diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 94d0365b31cd..9b225a7769f7 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -36,15 +36,15 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
 			       unsigned int *bytes_compl)
 {
 	if (buffer->unmap_len) {
-		struct pci_dev *pci_dev = tx_queue->efx->pci_dev;
+		struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
 		dma_addr_t unmap_addr = (buffer->dma_addr + buffer->len -
 					 buffer->unmap_len);
 		if (buffer->unmap_single)
-			pci_unmap_single(pci_dev, unmap_addr, buffer->unmap_len,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(dma_dev, unmap_addr, buffer->unmap_len,
+					 DMA_TO_DEVICE);
 		else
-			pci_unmap_page(pci_dev, unmap_addr, buffer->unmap_len,
-				       PCI_DMA_TODEVICE);
+			dma_unmap_page(dma_dev, unmap_addr, buffer->unmap_len,
+				       DMA_TO_DEVICE);
 		buffer->unmap_len = 0;
 		buffer->unmap_single = false;
 	}
@@ -138,7 +138,7 @@ efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr)
 netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 {
 	struct efx_nic *efx = tx_queue->efx;
-	struct pci_dev *pci_dev = efx->pci_dev;
+	struct device *dma_dev = &efx->pci_dev->dev;
 	struct efx_tx_buffer *buffer;
 	skb_frag_t *fragment;
 	unsigned int len, unmap_len = 0, fill_level, insert_ptr;
@@ -167,17 +167,17 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	fill_level = tx_queue->insert_count - tx_queue->old_read_count;
 	q_space = efx->txq_entries - 1 - fill_level;
 
-	/* Map for DMA.  Use pci_map_single rather than pci_map_page
+	/* Map for DMA.  Use dma_map_single rather than dma_map_page
 	 * since this is more efficient on machines with sparse
 	 * memory.
 	 */
 	unmap_single = true;
-	dma_addr = pci_map_single(pci_dev, skb->data, len, PCI_DMA_TODEVICE);
+	dma_addr = dma_map_single(dma_dev, skb->data, len, PCI_DMA_TODEVICE);
 
 	/* Process all fragments */
 	while (1) {
-		if (unlikely(pci_dma_mapping_error(pci_dev, dma_addr)))
-			goto pci_err;
+		if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
+			goto dma_err;
 
 		/* Store fields for marking in the per-fragment final
 		 * descriptor */
@@ -246,7 +246,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 		i++;
 		/* Map for DMA */
 		unmap_single = false;
-		dma_addr = skb_frag_dma_map(&pci_dev->dev, fragment, 0, len,
+		dma_addr = skb_frag_dma_map(dma_dev, fragment, 0, len,
 					    DMA_TO_DEVICE);
 	}
 
@@ -261,7 +261,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 
 	return NETDEV_TX_OK;
 
- pci_err:
+ dma_err:
 	netif_err(efx, tx_err, efx->net_dev,
 		  " TX queue %d could not map skb with %d bytes %d "
 		  "fragments for DMA\n", tx_queue->queue, skb->len,
@@ -284,11 +284,11 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	/* Free the fragment we were mid-way through pushing */
 	if (unmap_len) {
 		if (unmap_single)
-			pci_unmap_single(pci_dev, unmap_addr, unmap_len,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(dma_dev, unmap_addr, unmap_len,
+					 DMA_TO_DEVICE);
 		else
-			pci_unmap_page(pci_dev, unmap_addr, unmap_len,
-				       PCI_DMA_TODEVICE);
+			dma_unmap_page(dma_dev, unmap_addr, unmap_len,
+				       DMA_TO_DEVICE);
 	}
 
 	return rc;
@@ -651,17 +651,8 @@ static __be16 efx_tso_check_protocol(struct sk_buff *skb)
 	EFX_BUG_ON_PARANOID(((struct ethhdr *)skb->data)->h_proto !=
 			    protocol);
 	if (protocol == htons(ETH_P_8021Q)) {
-		/* Find the encapsulated protocol; reset network header
-		 * and transport header based on that. */
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
-		skb_set_network_header(skb, sizeof(*veh));
-		if (protocol == htons(ETH_P_IP))
-			skb_set_transport_header(skb, sizeof(*veh) +
-						 4 * ip_hdr(skb)->ihl);
-		else if (protocol == htons(ETH_P_IPV6))
-			skb_set_transport_header(skb, sizeof(*veh) +
-						 sizeof(struct ipv6hdr));
 	}
 
 	if (protocol == htons(ETH_P_IP)) {
@@ -684,20 +675,19 @@ static __be16 efx_tso_check_protocol(struct sk_buff *skb)
  */
 static int efx_tsoh_block_alloc(struct efx_tx_queue *tx_queue)
 {
-
-	struct pci_dev *pci_dev = tx_queue->efx->pci_dev;
+	struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
 	struct efx_tso_header *tsoh;
 	dma_addr_t dma_addr;
 	u8 *base_kva, *kva;
 
-	base_kva = pci_alloc_consistent(pci_dev, PAGE_SIZE, &dma_addr);
+	base_kva = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr, GFP_ATOMIC);
 	if (base_kva == NULL) {
 		netif_err(tx_queue->efx, tx_err, tx_queue->efx->net_dev,
 			  "Unable to allocate page for TSO headers\n");
 		return -ENOMEM;
 	}
 
-	/* pci_alloc_consistent() allocates pages. */
+	/* dma_alloc_coherent() allocates pages. */
 	EFX_BUG_ON_PARANOID(dma_addr & (PAGE_SIZE - 1u));
 
 	for (kva = base_kva; kva < base_kva + PAGE_SIZE; kva += TSOH_STD_SIZE) {
@@ -714,7 +704,7 @@ static int efx_tsoh_block_alloc(struct efx_tx_queue *tx_queue)
 /* Free up a TSO header, and all others in the same page. */
 static void efx_tsoh_block_free(struct efx_tx_queue *tx_queue,
 				struct efx_tso_header *tsoh,
-				struct pci_dev *pci_dev)
+				struct device *dma_dev)
 {
 	struct efx_tso_header **p;
 	unsigned long base_kva;
@@ -731,7 +721,7 @@ static void efx_tsoh_block_free(struct efx_tx_queue *tx_queue,
 			p = &(*p)->next;
 	}
 
-	pci_free_consistent(pci_dev, PAGE_SIZE, (void *)base_kva, base_dma);
+	dma_free_coherent(dma_dev, PAGE_SIZE, (void *)base_kva, base_dma);
 }
 
 static struct efx_tso_header *
@@ -743,11 +733,11 @@ efx_tsoh_heap_alloc(struct efx_tx_queue *tx_queue, size_t header_len)
 	if (unlikely(!tsoh))
 		return NULL;
 
-	tsoh->dma_addr = pci_map_single(tx_queue->efx->pci_dev,
+	tsoh->dma_addr = dma_map_single(&tx_queue->efx->pci_dev->dev,
 					TSOH_BUFFER(tsoh), header_len,
-					PCI_DMA_TODEVICE);
-	if (unlikely(pci_dma_mapping_error(tx_queue->efx->pci_dev,
-					   tsoh->dma_addr))) {
+					DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(&tx_queue->efx->pci_dev->dev,
+				       tsoh->dma_addr))) {
 		kfree(tsoh);
 		return NULL;
 	}
@@ -759,9 +749,9 @@ efx_tsoh_heap_alloc(struct efx_tx_queue *tx_queue, size_t header_len)
 static void
 efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, struct efx_tso_header *tsoh)
 {
-	pci_unmap_single(tx_queue->efx->pci_dev,
+	dma_unmap_single(&tx_queue->efx->pci_dev->dev,
 			 tsoh->dma_addr, tsoh->unmap_len,
-			 PCI_DMA_TODEVICE);
+			 DMA_TO_DEVICE);
 	kfree(tsoh);
 }
 
@@ -892,13 +882,13 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
 			unmap_addr = (buffer->dma_addr + buffer->len -
 				      buffer->unmap_len);
 			if (buffer->unmap_single)
-				pci_unmap_single(tx_queue->efx->pci_dev,
+				dma_unmap_single(&tx_queue->efx->pci_dev->dev,
 						 unmap_addr, buffer->unmap_len,
-						 PCI_DMA_TODEVICE);
+						 DMA_TO_DEVICE);
 			else
-				pci_unmap_page(tx_queue->efx->pci_dev,
+				dma_unmap_page(&tx_queue->efx->pci_dev->dev,
 					       unmap_addr, buffer->unmap_len,
-					       PCI_DMA_TODEVICE);
+					       DMA_TO_DEVICE);
 			buffer->unmap_len = 0;
 		}
 		buffer->len = 0;
@@ -927,7 +917,6 @@ static void tso_start(struct tso_state *st, const struct sk_buff *skb)
 	EFX_BUG_ON_PARANOID(tcp_hdr(skb)->syn);
 	EFX_BUG_ON_PARANOID(tcp_hdr(skb)->rst);
 
-	st->packet_space = st->full_packet_size;
 	st->out_len = skb->len - st->header_len;
 	st->unmap_len = 0;
 	st->unmap_single = false;
@@ -954,9 +943,9 @@ static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx,
 	int hl = st->header_len;
 	int len = skb_headlen(skb) - hl;
 
-	st->unmap_addr = pci_map_single(efx->pci_dev, skb->data + hl,
-					len, PCI_DMA_TODEVICE);
-	if (likely(!pci_dma_mapping_error(efx->pci_dev, st->unmap_addr))) {
+	st->unmap_addr = dma_map_single(&efx->pci_dev->dev, skb->data + hl,
+					len, DMA_TO_DEVICE);
+	if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
 		st->unmap_single = true;
 		st->unmap_len = len;
 		st->in_len = len;
@@ -1008,7 +997,7 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
 		buffer->continuation = !end_of_packet;
 
 		if (st->in_len == 0) {
-			/* Transfer ownership of the pci mapping */
+			/* Transfer ownership of the DMA mapping */
 			buffer->unmap_len = st->unmap_len;
 			buffer->unmap_single = st->unmap_single;
 			st->unmap_len = 0;
@@ -1181,18 +1170,18 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 
  mem_err:
 	netif_err(efx, tx_err, efx->net_dev,
-		  "Out of memory for TSO headers, or PCI mapping error\n");
+		  "Out of memory for TSO headers, or DMA mapping error\n");
 	dev_kfree_skb_any(skb);
 
  unwind:
 	/* Free the DMA mapping we were in the process of writing out */
 	if (state.unmap_len) {
 		if (state.unmap_single)
-			pci_unmap_single(efx->pci_dev, state.unmap_addr,
-					 state.unmap_len, PCI_DMA_TODEVICE);
+			dma_unmap_single(&efx->pci_dev->dev, state.unmap_addr,
+					 state.unmap_len, DMA_TO_DEVICE);
 		else
-			pci_unmap_page(efx->pci_dev, state.unmap_addr,
-				       state.unmap_len, PCI_DMA_TODEVICE);
+			dma_unmap_page(&efx->pci_dev->dev, state.unmap_addr,
+				       state.unmap_len, DMA_TO_DEVICE);
 	}
 
 	efx_enqueue_unwind(tx_queue);
@@ -1216,5 +1205,5 @@ static void efx_fini_tso(struct efx_tx_queue *tx_queue)
 
 	while (tx_queue->tso_headers_free != NULL)
 		efx_tsoh_block_free(tx_queue, tx_queue->tso_headers_free,
-				    tx_queue->efx->pci_dev);
+				    &tx_queue->efx->pci_dev->dev);
 }